Plugin

Pipeline giornaliera automatizzata di contenuti per Insta360 GO 3S: acquisizione remota BLE/WiFi di riprese d'acquario, importazione wireless, valutazione qualità ffmpeg con registro delle decisioni, montaggio automatico (selezione segmenti, narrazione TTS, musica, sottotitoli) e caricamento su Bilibili tramite biliup (dry-run per impostazione predefinita).

Bridge Telegram per DeepSeek Harness: sessioni bidirezionali, steering della conversazione, instradamento verso il canale home e note vocali TTS inviate come messaggi audio Telegram.

Chat vocale in stile Doubao per DSH: tenere premuto il microfono del compositore converte la voce in testo e invia automaticamente, e le risposte dell'IA vengono lette a voce alta. Condensazione opzionale tramite LLM (le risposte lunghe vengono riassunte in brevi frasi parlate, seguendo il modello della conversazione corrente), pulizia del testo adatta al TTS, voci Edge TTS selezionabili, arresto automatico al silenzio regolabile e impostazioni incorporate nella finestra di dialogo delle impostazioni di DSH.

Pronuncia le risposte dell'agente nell'interfaccia web di DeepSeek Harness tramite una catena di fallback dei fornitori (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), così un fornitore in errore o con limite di velocità passa al successivo invece di restare in silenzio.

Trasforma l'ultimo turno di sessione DSH completato in un video riepilogativo verticale condivisibile: storyboard modificabile di cinque scene, oscuramento della privacy lato host, rifinitura AI e narrazione TTS opzionali, esportazione MP4/WebM con copertina PNG.

Voce full-duplex local-first per DeepSeek Harness, orchestrata da Muxiva

Chiamate vocali avviate dall’agente: `offer_call` fa squillare l’umano (接听/拒接/稍后再说); le chiamate accettate vengono sintetizzate e riprodotte in locale con CrispASR + Qwen3-TTS (9 voci, 2 dialetti cinesi), mentre quelle rifiutate restituiscono la decisione all’agente.

Legge ad alta voce le risposte dell’assistente solo tramite Fish Audio API (porta la tua chiave): lettura per messaggio, interruttore di lettura automatica e una pagina impostazioni per modello, reference_id della voce, chiave API cifrata e proxy.

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatible /audio/speech endpoint, with voice, emotion, speed and model selection plus an auto-read toggle.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

MiniMax 语音识别（asr-1.0）+ 语音合成（speech-2.8-hd）的 DeepSeek Harness 全局插件：转写工具、任务结束后用喇叭念一句的播报、实时免手对话、303 个音色可选

Audio Copilot for DeepSeek Harness: transcribe audio (ASR) and synthesize speech (TTS) — gives text-only agents ears and a voice. Windows-local SAPI TTS out of the box; OpenAI-compatible ASR/TTS endpoints configurable. Includes an in-composer voice-input

Voce per DeepSeek Harness (dsh) — input speech-to-text + lettura ad alta voce TTS per DeepSeek solo testo, senza chiave API

Speaker button beside the composer microphone — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-drag-right picks any other reading start position on the page, press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Speaks a short status line when DSH changes state — turn done, turn error, job done, job failed, goal complete, goal blocked, an approval waiting, or the agent needs your answer — using eight pre-recorded clips in Chinese (default) and English. The audio is played by the host process through ffplay, or through the Windows PowerShell player that ships with the OS, so it does not depend on a Web Audio tab. Windows only.

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.

Adds a speaker button immediately right of the Like button on every finalized assistant reply; click it to hear the reply through the browser speech engine, and hover it for a speed and voice panel.

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.

Live2D avatar stage and desktop companion for DSH: bundled Haru sample, custom Cubism 2/3+ model loading with scale and position controls, a draggable in-page pet, an optional transparent always-on-top desktop pet window, per-conversation expression prompt control, and opt-in voice with self-hosted ASR/TTS.

DeepSeek Harness plugin: turn lines of narration into a finished vertical reel. Free neural voice-over, burned-in captions, no API keys.

XiaoShuang desktop pet for DSH: six-layer memory, persona injection, mood-driven video avatar, manual emotion menu, and TTS replies.

Voice for the DeepSeek Harness: speak to the agent, hear it back, and see what it is doing from a floating window that stays on top of whatever you are running.